-
According to the leaderboard on SemanticKITTI competition, KPConv shows worse performance compared to other volumetric methods. Is there any reason on this phenomenon? By the way, thanks for sharing y…
-
Thanks for your amazing work, and I'm care about the time of training consuming.
My GPU is RTX 3090(single), I found the maximum of memory occupancy is around 16G, and each iteration consumes aroun…
lzhnb updated
3 years ago
-
Hi! An earlier version of evaluate.py on `SemanticKITTI_val_SPVNAS@65GMACs` worked fine when I tested it a few months back, but the latest code produces a weird error `ValueError: Input feature size a…
-
@YangZhang4065 @Xyouz thanks for sharing the source code , can you please let me know what is the use of functions like
" SemKITTI2train_single(label):" and "SemKITTI2train(label):" which is used …
-
Hi, I followed the instructions in README
`torchpack dist-run -np 1 python evaluate.py configs/semantic_kitti/default.yaml --name SemanticKITTI_val_SPVNAS@65GMACs`
I wonder if there is any step I m…
-
What type of GPU did u use and how long did u train on the SemanticKITTI?
-
hi, @HuguesTHOMAS
as the data flow show:
```python
def SemanticKittiCollate(batch_data):
batch = SemanticKittiCustomBatch(batch_data)
return batch, batch.labels
```
`input_list = input…
-
I suspect the SparseConvUnet (torch) ScanNet checkpoint is broken. When I run the following code:
```
import os
import open3d.ml as _ml3d
import open3d.ml.torch as ml3d
cfg_file = "./sparseco…
-
Hi:
Thanks for sharing your excellent work.
As you've mentioned in your paper that you've tested your approaches on three different dataset, including SemanticKITTI, A2D2 and Paris-Lille-3D.
Woul…
-
Thanks for your excellent work! The ending criteria for testing SemanticKitti test Dataset(with on_val=False) seems to require the minimum Frame Potentials greater than 100? And I don't understand wha…